Menu
SkillsMP has collected 37 skills from idealic-ai/engine. Open a skill to review its source and details.
Showing 37 of 37 collected skills.
A wave-based grooming pass over a Linear Project's feedback inbox: one session drains new inbox comments, organizes + consolidates them, triages each signal toward an outcome (graduate to a ticket, dispatch light triage, or marinate), then closes with a…
Post an item into a project's intake inbox — resolves the Linear Project, classifies the item into the best-fit inbox channel, fills that channel's reporter template, and posts it as a comment. The quick front-door companion to /intake (which then organizes,…
Systematic diagnosis and repair of bugs, failures, and regressions — structured triage before action, with two walk-throughs (issues + fixes). Supports goal-based modes: General (standard investigate-fix-verify), TDD (test-first discipline), Hotfix…
Interactive agent fleet designer - configure your multi-agent workspace. Triggers: "configure fleet", "setup agents", "multi-agent workspace", "fleet layout".
Drives feature implementation following structured development protocols. Triggers: "implement this feature", "build this", "write the code", "TDD implementation", "execute the plan".
Compile the detective evidence for a resolved body of work into a self-contained, shareable visual PROOF — the real artifacts (code blocks, PDF pages, screenshots, logs, CLI output, overlays, diagrams), a structure that makes the claim legible at a glance,…
Checkpoint a body of work: a reviewer subagent actively VERIFIES the work read-only (runs gates to confirm 'done' claims), checks it's ON-DIRECTION with the ticket's intent, and finds LEFTOVERS. Then, on your confirm, the orchestrator COMMITS the work scoped…
Surface RELATED and DUPLICATE Linear tickets for the work in front of you, before you build. A read-only subagent runs `engine ticket-search` (standalone) or navigates the startup SRC_RELATED_TICKETS candidates (session-startup), deep-reads each promising…
Turn in-context work into one OR MORE well-framed tickets. A background agent analyzes the scope and drafts PREMISE-FIRST issues (problem, intent/why, constraints, non-goals, acceptance signals — NOT an algorithm), you calibrate each via questions, then it…
Convene a diverse expert panel over an explicitly targeted body of work — plan, diff, PR, commit, files, build-report, doc, brainstorm, or session — via a self-contained Council Brief, fan out N independent expert sub-agents IN PARALLEL (generatively selected…
Thorough analysis of code, architecture, or topics — produces a structured research report. Supports goal-based modes: Explore (general research), Audit (risk-focused critique), Improve (actionable suggestions), Custom (user-defined lens). Triggers: "analyze…
Hands-on hypothesis probe — actually TRY something to answer a question rather than just read about it: reproduce a suspected behavior, hack a proof-of-concept, test whether an approach is feasible. A subagent runs the experiment in-tree (uncommitted,…
Quick, read-only investigation delegated to a subagent: state an INTENT (a question you need answered) and it goes and finds out — sweeping the codebase, the database (read-only SELECTs), and tickets (Linear) as the question demands, thinking in the /analyze…
Hand a scoped implementation task to a builder sub-agent with a COMPLETE context pack assembled from the active session (goal, verbatim asks, plan slice, prior-chunk history, the whys, hard gates, scope guard), get back a structured Build Report to the…
Open a pull request for the current branch with a CONTEXT-MAXED body. A PR-writer subagent reads the branch commits + diff, the linked ticket(s), and the full builds/ trail (build reports, critiques, verdicts, decisions) to draft a rich PR description —…
Get back into the flow of a session in one glance. A read-only ORIENTATION report — not what-did-we-do-and-was-it-good (that's /summarize) but where do things stand RIGHT NOW: what work was done, where the branch is (git), where the ticket stands (Linear),…
Adversarially critique a body of work with a sub-agent, triage each finding with the user (fix / skip / defer), then apply the approved fixes inline or via a fixer sub-agent that knows the original goal + the critique + the resolution plan. Triggers:…
Catch yourself up on a body of work and review it. This is an inward, read-only report over a dynamically-scoped chunk OR the whole session. A reader subagent digests the trail (log / plan / DIALOGUE / builds / git) into a distilled, intent-oriented report: a…
Creates ASCII flowgraph diagrams using the `§CMD_FLOWGRAPH` notation — control-flow (decisions, branches, loops) AND trajectory/timeline graphs (status-annotated nodes: done/upcoming/dropped/stale, checkpoints, current-position). The single canonical…
Drive a ticket discussion turn — subscribe, ask/reply on a Linear ticket via MCP, notify local sibling agents, and keep a background watcher armed so replies wake you. Triggers: "ask on the ticket", "reply on FIN-1234", "discuss this in the ticket",…
High-level project vision designer — splits work into sequential or parallel chapters, defines decision principles, produces structured plans consumable by /coordinate. Triggers: "create a direct", "design a project vision", "plan the project", "split this…
Structured ideation and trade-off analysis for design and architecture decisions. Triggers: "brainstorm ideas", "explore this problem", "think through trade-offs", "challenge assumptions", "discuss architecture".
Reviews and validates work across sessions for consistency and correctness. Triggers: "review session work", "validate debriefs", "approve session reports", "end-of-day review".
Executes routine maintenance and cleanup tasks from a structured task queue. Triggers: "do some chores", "housekeeping tasks", "small cleanup tasks", "work through a task queue".
Worker-side claiming of delegated work items. Scans #delegated-X tags, presents items for claiming, routes to target skills. Triggers: "claim work", "pick up delegated items", "what's available to work on", "delegation claim".
Routes tagged work items to workers via async, blocking, or silent delegation. Triggers: "delegate this", "route this work", "hand off this task", "delegation create".
Standalone dispatch approval — scans #needs-X tags, presents grouped approval menu, executes tag transitions. Triggers: "review delegations", "dispatch approval", "what needs dispatching", "delegation review".
Lightweight session for quick ad-hoc work. No interrogation, no planning — just activate, work, and close. Triggers: "quick task", "just do this", "/do this", "ad-hoc work".
Keeps documentation in sync with code changes and project state. Triggers: "update documentation", "patch the docs", "sync docs with code changes", "update architecture docs".
Creates, edits, or promotes skills — scaffolds SKILL.md and assets to project-local or shared engine. Triggers: "create a new skill", "edit a skill", "scaffold a skill", "promote a skill", "add a project skill", "create a new command".
Smart assistant for the workflow engine — answers questions, invokes scripts, and navigates docs. Triggers: "engine help", "how does the engine work", "run an engine command", "what scripts are available".
Analyzes transcripts, session artifacts, or feedback to identify and apply protocol improvements across commands, directives, phases, and skills. Triggers: "improve the protocol", "analyze this session for improvements", "protocol audit", "fix the wording…
Hypothesis-driven iteration engine for LLM workloads — runs cycles of hypothesize, execute, review, analyze, decide, edit. Triggers: "iterate on this", "run a loop", "hypothesis-driven refinement", "improve the prompt", "tune the model".
Full research cycle — refines query, calls Gemini Deep Research, polls, delivers report. Triggers: "research this topic", "run a research cycle", "call Gemini Deep Research".
Smart assistant for session management — search sessions, check status, restart, continue after overflow. Triggers: "session status", "search sessions", "session find".
Designs and writes test cases for code correctness and regression prevention. Supports goal-based modes: Coverage (gap-filling), Hardening (edge cases & stress), Integration (boundaries & contracts), Custom (user-defined lens). Triggers: "write tests",…
Creates semi-permanent situational documents in project docs folders. Lightweight skill — no session, no logs, just focused writing. Triggers: "write up", "writeup".